DBRSNet: a dual-branch remote sensing image segmentation model based on feature interaction and multi-scale feature fusion

Abstract High-resolution images encapsulate abundant geographical information; however, precise semantic segmentation is essential for effective remote sensing image interpretation. Remote sensing semantic segmentation categorizes pixel-level image information into distinct land cover types, providi...

Full description

Saved in:
Bibliographic Details
Main Authors: Yong Ji, Wenbin Shi, Jingsheng Lei, Jiayin Ding
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-13236-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763250012422144
author Yong Ji
Wenbin Shi
Jingsheng Lei
Jiayin Ding
author_facet Yong Ji
Wenbin Shi
Jingsheng Lei
Jiayin Ding
author_sort Yong Ji
collection DOAJ
description Abstract High-resolution images encapsulate abundant geographical information; however, precise semantic segmentation is essential for effective remote sensing image interpretation. Remote sensing semantic segmentation categorizes pixel-level image information into distinct land cover types, providing essential support for urban planning, resource management, and environmental monitoring. However, existing approaches encounter two major challenges: insufficient retention of fine-grained local details and suboptimal global contextual modeling, especially in intricate and high-resolution remote sensing scenarios. These limitations result in fragmented object boundaries, degradation of small-scale structures, and challenges in comprehending large-scale spatial dependencies. To address these limitations, we introduce DBRSNet, an advanced dual-branch remote sensing segmentation framework that integrates feature interaction with multi-scale feature fusion. In DBRSNet, the Feature-Guided Selection Module (FGSM) adaptively integrates complementary features from CNN and Transformer branches, while the Convolutional Attention Integration Module (CAIM) enhances global dependencies and spectral correlations, ensuring a more comprehensive feature representation. Extensive evaluations on the ISPRS Vaihingen and ISPRS Potsdam datasets validate that DBRSNet surpasses 14 cutting-edge remote sensing segmentation models across all assessment metrics, highlighting its exceptional performance and competitiveness.
format Article
id doaj-art-8ca3c8178bb940a9b5447f340df12f7b
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-8ca3c8178bb940a9b5447f340df12f7b2025-08-20T03:05:27ZengNature PortfolioScientific Reports2045-23222025-07-0115111610.1038/s41598-025-13236-4DBRSNet: a dual-branch remote sensing image segmentation model based on feature interaction and multi-scale feature fusionYong Ji0Wenbin Shi1Jingsheng Lei2Jiayin Ding3School of Computer Science and Technology, Zhejiang University of Science and TechnologySchool of Computer, Hangzhou Dianzi UniversitySchool of Computer Science and Technology, Zhejiang University of Science and TechnologySchool of Computer Science and Technology, Zhejiang University of Science and TechnologyAbstract High-resolution images encapsulate abundant geographical information; however, precise semantic segmentation is essential for effective remote sensing image interpretation. Remote sensing semantic segmentation categorizes pixel-level image information into distinct land cover types, providing essential support for urban planning, resource management, and environmental monitoring. However, existing approaches encounter two major challenges: insufficient retention of fine-grained local details and suboptimal global contextual modeling, especially in intricate and high-resolution remote sensing scenarios. These limitations result in fragmented object boundaries, degradation of small-scale structures, and challenges in comprehending large-scale spatial dependencies. To address these limitations, we introduce DBRSNet, an advanced dual-branch remote sensing segmentation framework that integrates feature interaction with multi-scale feature fusion. In DBRSNet, the Feature-Guided Selection Module (FGSM) adaptively integrates complementary features from CNN and Transformer branches, while the Convolutional Attention Integration Module (CAIM) enhances global dependencies and spectral correlations, ensuring a more comprehensive feature representation. Extensive evaluations on the ISPRS Vaihingen and ISPRS Potsdam datasets validate that DBRSNet surpasses 14 cutting-edge remote sensing segmentation models across all assessment metrics, highlighting its exceptional performance and competitiveness.https://doi.org/10.1038/s41598-025-13236-4
spellingShingle Yong Ji
Wenbin Shi
Jingsheng Lei
Jiayin Ding
DBRSNet: a dual-branch remote sensing image segmentation model based on feature interaction and multi-scale feature fusion
Scientific Reports
title DBRSNet: a dual-branch remote sensing image segmentation model based on feature interaction and multi-scale feature fusion
title_full DBRSNet: a dual-branch remote sensing image segmentation model based on feature interaction and multi-scale feature fusion
title_fullStr DBRSNet: a dual-branch remote sensing image segmentation model based on feature interaction and multi-scale feature fusion
title_full_unstemmed DBRSNet: a dual-branch remote sensing image segmentation model based on feature interaction and multi-scale feature fusion
title_short DBRSNet: a dual-branch remote sensing image segmentation model based on feature interaction and multi-scale feature fusion
title_sort dbrsnet a dual branch remote sensing image segmentation model based on feature interaction and multi scale feature fusion
url https://doi.org/10.1038/s41598-025-13236-4
work_keys_str_mv AT yongji dbrsnetadualbranchremotesensingimagesegmentationmodelbasedonfeatureinteractionandmultiscalefeaturefusion
AT wenbinshi dbrsnetadualbranchremotesensingimagesegmentationmodelbasedonfeatureinteractionandmultiscalefeaturefusion
AT jingshenglei dbrsnetadualbranchremotesensingimagesegmentationmodelbasedonfeatureinteractionandmultiscalefeaturefusion
AT jiayinding dbrsnetadualbranchremotesensingimagesegmentationmodelbasedonfeatureinteractionandmultiscalefeaturefusion